GestaltLabs/DeepSeek-V4-Flash-0731-Ornstein
Text Generation • Updated • 1
E.M. Rabani PRO
SkyMind
AI & ML interests
Neuromorphic NNs
Recent Activity
liked a model about 7 hours ago
GestaltLabs/DeepSeek-V4-Flash-0731-Ornstein liked a model about 8 hours ago
TokenRhythm/NeoHorse-1-4BOrganizations
None yet
liked a
model about 7 hours ago
reacted to OppaAI's post with 🔥 about 7 hours ago
Post
300
Another small 4B model comes out yesterday.
NeoHorse 1 4B
TokenRhythm/NeoHorse-1-4B
There are quite a few good smaller parameter models that are capable for Agentic tasks:
The ones from the chart, I have tried a few already in my Jetson Orin Nano,
❌Gemma4 E2B IT - cannot fit my RAM usage if use with TTS and embedder
❓Qwen3.5 4B - just barely fit my RAM usage, need to add think/no_think
❌Spark X2.5 4B - need to build the forked llama.cpp; no vision
➡️Nanbeige 4.2 3B - need to build the forked llama.cpp; slower than Ministral3-3B by 25%; no vision but good for coding; maybe run this is separate server for doing coding tasks
➡️Agents A1 4B - This one is quite interesting. Another Qwen3.5 4B base. I just learnt this right now. This model may surpassed the Ministral3-3B that I'm currently running.
➡️NeoHorse 1 4B - wait for GGUF version comes out; Qwen 3.5 4B base with vision striped
➡️Needle2 45M - need to use separately from llama.cpp server; currently testing to see if it can be used as spawning sub-agents to do parallel tasks
NeoHorse 1 4B
TokenRhythm/NeoHorse-1-4B
There are quite a few good smaller parameter models that are capable for Agentic tasks:
The ones from the chart, I have tried a few already in my Jetson Orin Nano,
❌Gemma4 E2B IT - cannot fit my RAM usage if use with TTS and embedder
❓Qwen3.5 4B - just barely fit my RAM usage, need to add think/no_think
❌Spark X2.5 4B - need to build the forked llama.cpp; no vision
➡️Nanbeige 4.2 3B - need to build the forked llama.cpp; slower than Ministral3-3B by 25%; no vision but good for coding; maybe run this is separate server for doing coding tasks
➡️Agents A1 4B - This one is quite interesting. Another Qwen3.5 4B base. I just learnt this right now. This model may surpassed the Ministral3-3B that I'm currently running.
➡️NeoHorse 1 4B - wait for GGUF version comes out; Qwen 3.5 4B base with vision striped
➡️Needle2 45M - need to use separately from llama.cpp server; currently testing to see if it can be used as spawning sub-agents to do parallel tasks
- 3 replies
liked a
model about 8 hours ago
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF
#12245 opened 1 day ago
by SkyMind
liked a
model 3 days ago
liked a
model 4 days ago
liked a
Space 5 days ago
liked a
model 6 days ago
reacted to Bc-AI's post with 🔥 7 days ago
Post
2526
Building a 6.58B sparse MoE model from scratch on a single GPU.
Hey everyone! Today is day 1 of training Smilyai-Lab's new model I call G1-MINI. It's basically the smaller version of our planned model G1 which will be 20B and activate about 2B per token. MINI activates about 1.16B params per token and is currently training right now. If no errors spring up now, I'd say i can launch sometime around September 15th~ish. Thanks to our beta testers:
@guardamarcos
@ProCreations
@juiceb0xc0de
@Timmy6767
@Sbui503
@atom77777
@Fishtiks
@smartdigitalnetworks
@EmetTheGolum
@smilyai-large-team
@MUK-IS-GOAT
@Bc-AI
@Banaxi-Tech
@vovaRL
@Datdanboi25
Hey everyone! Today is day 1 of training Smilyai-Lab's new model I call G1-MINI. It's basically the smaller version of our planned model G1 which will be 20B and activate about 2B per token. MINI activates about 1.16B params per token and is currently training right now. If no errors spring up now, I'd say i can launch sometime around September 15th~ish. Thanks to our beta testers:
@guardamarcos
@ProCreations
@juiceb0xc0de
@Timmy6767
@Sbui503
@atom77777
@Fishtiks
@smartdigitalnetworks
@EmetTheGolum
@smilyai-large-team
@MUK-IS-GOAT
@Bc-AI
@Banaxi-Tech
@vovaRL
@Datdanboi25
- 9 replies
reacted to RiverRider's post with 🔥 7 days ago
Post
2737
Where the Hivemind Comes From: Geometry, Tuning and Format, Separated on Open Weights
“First, representations are mutually recoverable. On 12 open-weight models from 8 labs, a ridge map from one model's hidden states to another's retrieves the right held-out item 0.9181 of the time across lab boundaries, against a shuffled floor of 0.00101 and a self-map ceiling of 0.999. Shared corporate lineage is worth only 0.0357 of that.”
“Second, base models do not reproduce the reported level. Under the original study's own sampling settings, our base models reach intra-model 0.3644 and inter-model 0.3401 on a floor of 0.0993 that matches theirs, and zero of 720 model-prompt cells clear 0.8. The floors agree while the signal differs by more than a factor of two, so this is not a scale artifact.”
“Third, and decisively, we recover their level and isolate its cause. Using six matched base/instruct pairs, holding pretrained weights, prompts, decoding and scorer fixed, instruction tuning alone raises intra-model similarity by 0.0786. The same tuned weights prompted through the model's own chat template raise it by 0.3623, reaching 0.7272, with four of six models exceeding 0.80 and reproducing the band reported for frontier systems from models of 0.6B to 2B. The prompt format does roughly 4.6 times the work of the tuning.”
paper attached 🧾
https://huggingface.co/blog/RiverRider/where-the-hivemind-comes-from-geometry-tuning-and
“First, representations are mutually recoverable. On 12 open-weight models from 8 labs, a ridge map from one model's hidden states to another's retrieves the right held-out item 0.9181 of the time across lab boundaries, against a shuffled floor of 0.00101 and a self-map ceiling of 0.999. Shared corporate lineage is worth only 0.0357 of that.”
“Second, base models do not reproduce the reported level. Under the original study's own sampling settings, our base models reach intra-model 0.3644 and inter-model 0.3401 on a floor of 0.0993 that matches theirs, and zero of 720 model-prompt cells clear 0.8. The floors agree while the signal differs by more than a factor of two, so this is not a scale artifact.”
“Third, and decisively, we recover their level and isolate its cause. Using six matched base/instruct pairs, holding pretrained weights, prompts, decoding and scorer fixed, instruction tuning alone raises intra-model similarity by 0.0786. The same tuned weights prompted through the model's own chat template raise it by 0.3623, reaching 0.7272, with four of six models exceeding 0.80 and reproducing the band reported for frontier systems from models of 0.6B to 2B. The prompt format does roughly 4.6 times the work of the tuning.”
paper attached 🧾
https://huggingface.co/blog/RiverRider/where-the-hivemind-comes-from-geometry-tuning-and
- 12 replies
liked 3
models 11 days ago
liked a
model 12 days ago
upvoted a paper 13 days ago
liked a
dataset 14 days ago
liked 2
models 14 days ago
liked 2
models 16 days ago
